MIT-licensed, local-first context graph for DeepSeek Harness (dsh): a canvas view where wires decide what the model sees next, plus read-only MCP search across your local agent sessions. Requires Node 22.19+ and DSH 0.1.2-rc+.
DSH integration
Native runtime
Author-claimed
Safety audit
Unaudited
Last verified
2026-09-06
License
MIT
01What can it help you accomplish?
Recover the exact past conversation that introduced a code change or a concept
The matching turn across your local Claude Code, Codex, DeepSeek Harness and ThoughtDAG sessions, with the file/line or phrase it referenced
Developers and researchers who want to recover decision context from scattered agent logs instead of re-reading everything
Cut contaminated context and improve the next answer
A cleaner answer after deleting a wire, with less irrelevant history and fewer context-driven hallucinations
Anyone using LLMs who wants visible, editable control over what the model sees next
02How to install into DeepSeek Harness
Prerequisites
- Node 22.19+ (the README states "Requires Node 22.19+ and DeepSeek Harness 0.1.2-rc or later")
- DeepSeek Harness 0.1.2-rc or later
Installation steps
- 01
Run `dsh plugin --profile web add dsh-thoughtdag` to add the web plugin
$ dsh plugin --profile web add dsh-thoughtdag
- 02
Run `dsh web` to open the harness web UI and use the 对话 | 思维图 switch
$ dsh web
Verify the integration
Not specified by the author
03DSH integration and capability boundaries
Installed as a DSH web plugin (`dsh plugin --profile web add dsh-thoughtdag`); renders as a canvas view inside the harness web UI (对话 | 思维图 switch)
Read-only MCP context search
a code file, an exact phrase, a URL, or a paper→the matching turn across your local Claude Code, Codex, DeepSeek Harness and ThoughtDAG sessions
Editable context canvas (Session Atlas)
agent sessions and nodes→a merged, editable thought graph; continue from any node and bring the result back to the graph
Source sessions remain read-onlyHarness-native model calls
a question asked on the canvas→the answer streams back into the node and stays in the harness session log
Local-first backup & Thought Map export
the canvas→automatic folder backup of real files; export of the node/wire structure as a light or dark Thought Map
04Who is it for? When not to use it?
Good for
- Developers and researchers who want to recover decision context from scattered agent logs instead of re-reading everything
- Anyone using LLMs who wants visible, editable control over what the model sees next
Not for
- Requires Node 22.19+ and DeepSeek Harness 0.1.2-rc or later — older Node or DSH versions are not supported.
05Compatibility, maintenance and safety notes
- Requires Node 22.19+ and DeepSeek Harness 0.1.2-rc or later — older Node or DSH versions are not supported.
- Source agent sessions stay read-only; ThoughtDAG indexes and mirrors them but does not modify the original logs.
- Session Atlas currently supports local Claude Code, Codex and DeepSeek Harness sessions, with more agent integrations still in development.
readme_verified
06Frequently asked questions
How do I install ThoughtDAG inside DeepSeek Harness?
Run `dsh plugin --profile web add dsh-thoughtdag`, then `dsh web`. The plugin bundles the canvas, so no separate ThoughtDAG install is needed — just Node 22.19+ and DeepSeek Harness 0.1.2-rc or later.
Does ThoughtDAG need its own API key in the harness?
No. Inside DeepSeek Harness, model calls use the harness's own providers and keys; ThoughtDAG adds no key of its own, and images and link fetches go through the harness's attachment store.
What does the canvas do to the model context?
Wires are the context: what wires into a node is exactly what the model sees next. Delete a wire and ask again, and the same prompt returns a different answer — you edit the graph, you edit the model's memory.
Which agent sessions can Session Atlas bring onto the canvas?
Currently local Claude Code, Codex and DeepSeek Harness sessions. Source sessions stay read-only, and more agent integrations are in development.
Is my data local?
Yes. In the desktop app everything lives on your machine — canvases, keys, documents — and PDFs never leave your machine. The web demo runs model traffic browser-direct, with keys never touching the server.
07Related DSH workflows
weknora
by tencent
Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.
honcho
by plastic-labs
Memory library for building stateful agents
mirage
by strukto-ai
The World's First Virtual Terminal for AI Agents
reme
by agentscope-ai
ReMe: Memory Management Kit for Agents - Remember Me, Refine Me.
08Data and sources
ThoughtDAG runs as a view inside the DeepSeek Harness web UI: a 对话 | 思维图 switch above the chat.
The canvas is where you decide what the harness sees next; the harness runs the turn.
This page is generated from the project’s public documentation, repository metadata and a structured parse of DSH Plugins; last verified on 2026-09-06. Found an error? Submit a correction.
Best DeepSeek Harness Plugins
Twelve plugins worth installing first — picked from the whole catalog, across every category.